Hi,
I have a question about which dissimilarity/linkage methods is more appropriate to apply to resting stage ICs.
For example, with the output of melodic I get a number of components. Now I am interested in calculating the distance measure and linkage method to do hierarchical clustering
DO I perform dissimilar based on corrections and if yes, (which one? 1- cor or 1- abs)?
Dissimilarity = 1 - Correlation
Dissimilarity = 1 - Abs(Correlation)
plot(hclust(distance) I think here the linkage method is 'complete'. Is that correct?
OR do I perform:
euclidean followed by ward or average linkage
dist(data,method = "euclidean")
hclust(method = "ward") or "average"
Thank you, Jasmin
########################################################################
To unsubscribe from the FSL list, click the following link:
https://www.jiscmail.ac.uk/cgi-bin/webadmin?SUBED1=FSL&A=1
|